On the Adaptability of Recurrent Neural Networks for Real-Time Jazz Improvisation Accompaniment

Frontiers in Artificial Intelligence

Theatina Kylafi¹  Aggelos Pikrakis²  Kosmas Kritsis³  Maximos Kaliakatsos-Papakostas³  Vassilis Katsouros³ 

[1] Department of Informatics and Telecommunications, National and Kapodistrian University of Athens, Athens, Greece;Department of Informatics, University of Piraeus, Piraeus, Greece;Institute for Language and Speech Processing, Athena Research Center, Athens, Greece;

关键词: automatic accompaniment system;    music generative system;    real-time music interaction;    music improvisation;    machine learning;    long short-term memory;   

DOI  :  10.3389/frai.2020.508727

来源: DOAJ

【 摘 要 】

Jazz improvisation on a given lead sheet with chords is an interesting scenario for studying the behaviour of artificial agents when they collaborate with humans. Specifically in jazz improvisation, the role of the accompanist is crucial for reflecting the harmonic and metric characteristics of a jazz standard, while identifying in real-time the intentions of the soloist and adapt the accompanying performance parameters accordingly. This paper presents a study on a basic implementation of an artificial jazz accompanist, which provides accompanying chord voicings to a human soloist that is conditioned by the soloing input and the harmonic and metric information provided in a lead sheet chart. The model of the artificial agent includes a separate model for predicting the intentions of the human soloist, towards providing proper accompaniment to the human performer in real-time. Simple implementations of Recurrent Neural Networks are employed both for modeling the predictions of the artificial agent and for modeling the expectations of human intention. A publicly available dataset is modified with a probabilistic refinement process for including all the necessary information for the task at hand and test-case compositions on two jazz standards show the ability of the system to comply with the harmonic constraints within the chart. Furthermore, the system is indicated to be able to provide varying output with different soloing conditions, while there is no significant sacrifice of “musicality” in generated music, as shown in subjective evaluations. Some important limitations that need to be addressed for obtaining more informative results on the potential of the examined approach are also discussed.

【 授权许可】

Unknown